Author Identifier
Thair S. Mahmoud: https://orcid.org/0000-0001-5060-1136
Document Type
Journal Article
Publication Title
Renewable Energy
Volume
239
Publisher
Elsevier
School
School of Engineering
RAS ID
77104
Abstract
The transition of electricity generation from firm to non-firm renewable generation is driving changes in wholesale electricity price dynamics that are increasingly challenging to model due to the stochastic nature of wind and solar as the primary energy source. Robust pricing models are essential for optimising financial performance in liberalised electricity markets. The novelty of this paper is the application of Bayesian Belief Networks in the modelling of wholesale electricity price formation, specifically in power systems with a high penetration of non-firm renewable generation. This paper links the mathematical Bayesian representation to established statistical and computational approaches using a functional supply-side wholesale electricity market pricing model. In addition, the paper introduces a novel validation method employing volatility analysis to assess the case study's performance. The case study revealed that when the proportion of stochastic generation was ≥40 % penetration in a trading interval, the Bayesian Belief Network model's accuracy considerably outperformed the benchmark model with a Mean Absolute Scale Error of 1.43 compared to 1.63 in those intervals. Finally, the volatility analysis results challenged the prevailing notion of a positive causal relationship between non-firm renewable penetration and price volatility.
DOI
10.1016/j.renene.2024.122045
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Comments
Maticka, M. J., & Mahmoud, T. S. (2025). Bayesian Belief Networks: Redefining wholesale electricity price modelling in high penetration non-firm renewable generation power systems. Renewable Energy, 239. https://doi.org/10.1016/j.renene.2024.122045